Data Processing Method and Data Comparing Method

1. A method for processing time series data generated at a substrate treating facility, the method comprising: dividing a first data of a first facility according to each process of substrate treating by the first facility; dividing a second data of a second facility according to each process of substrate treating by the second facility; converting the divided first data and the divided second data to a same size using 1D convolution, wherein the same size is a data size for input to a Siamese network; assembling the converted first data and the converted second data into a first plane and a second plane, respectively, wherein each of the first plane and the second plane includes a 2D convolution representing an individual process of substrate treating; combining a plurality of 2D convolutions to generate a 3D convolution, wherein each 2D convolution of the plurality of 2D convolutions represents a separate and distinct process of substrate treating; and determining, using the Siamese network, whether the assembled first data and the assembled second data are the same.

2. The method of claim 1, wherein the same size is a greatest data among the divided data.

3. The method of claim 1, wherein the same size is a data size for input to a Siamese network.

4. The method of claim 1, wherein assembling the converted data with the same size includes assembling the converted data into a single plane.

5. A computer-readable recording medium having a program for executing the method of claim 4.

6. The method of claim 1, wherein assembling the converted data with the same size includes assembling the converted data to generate a 2D convolution representing an individual process of substrate treating.

7. The method of claim 6, further comprising: combining a plurality of 2D convolutions to generate a 3D convolution, wherein each 2D convolution of the plurality of 2D convolutions represents a separate and distinct process of substrate treating.

8. A method for comparing time series data generated at a substrate treating of a first facility and data of a second facility, the method comprising: pre-processing first data of the first facility, wherein pre-processing first data of the first facility includes: dividing the first data of the first facility according to each process of a substrate treating by the first facility; and converting the divided first data to a same size using 1D convolution, wherein the same size is a data size for input to a Siamese network; pre-processing second data of the second facility, wherein pre-processing second data of the second facility includes: dividing the second data of the second facility according to each process of a substrate treating by the second facility; and converting the divided second data to a same size using 1D convolution, wherein the same size is the data size for input to the Siamese network; assembling the pre-processed first data and second data into a first plane and a second plane, respectively, wherein each of the first plane and the second plane includes a 2D convolution representing an individual process of substrate treating; combining a plurality of 2D convolutions to generate a 3D convolution, wherein each 2D convolution of the plurality of 2D convolutions represents a separate and distinct process of substrate treating; and determining, using the Siamese network, whether the assembled first data and the second data are the same.

9. The method of claim 8, wherein the same size is a greatest data among the divided first data and the divided second data, respectively.

10. The method of claim 8, wherein the same size is a data size for input to a Siamese network.

11. The method of claim 9, further comprising assembling the converted first data.

12. The method of claim 11, further comprising assembling the converted second data.

13. The method of claim 12, wherein the determining whether the pre-processed first data of the first facility and the pre-processed second data of the second facility are the same comprises determining using a Siamese network.

14. The method of claim 13, further comprising determining, by the Siamese network, the similarity of data between the assembled first data and the assembled second data.

15. A computer-readable recording medium having a program for executing the method of claim 14.

16. A non-transitory computer-readable medium including one or more programs that, when executed by a computer, perform a method for comparing time series data generated at a plurality of substrate treating facilities, the method comprising: dividing a first data of a first facility according to each process of substrate treating by the first facility; dividing a second data of a second facility according to each process of substrate treating by the second facility; converting the divided first data and the divided second data to a same size using 1D convolution, wherein the same size is a data size for input to a Siamese network; assembling the converted first data and the converted second data into a first plane and a second plane, respectively, wherein each of the first plane and the second plane includes a 2D convolution representing an individual process of substrate treating; combining a plurality of 2D convolutions to generate a 3D convolution, wherein each 2D convolution of the plurality of 2D convolutions represents a separate and distinct process of substrate treating; and determining, using the Siamese network, whether the assembled first data and the assembled second data are the same.

17. The non-transitory computer-readable medium of claim 16, wherein the 1D convolution is provided as a fixed value.